OpenLogi macOS Permissions Triage
AprilNEA/OpenLogi
Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.
Evidence-before-action diagnosis of failing ML experiments. An agent skill from fcakyon/phd-skills.
Install Debug
$ npx skills add fcakyon/phd-skills --skill debug -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install fcakyon/phd-skills debug --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/fcakyon/phd-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/debug .claude/skills/debug && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "debug" agent skill from https://github.com/fcakyon/phd-skills/tree/main/plugin/skills/debug into .claude/skills/debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debug", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/fcakyon/phd-skills/tree/main/plugin/skills/debugType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add fcakyon/phd-skills --skill debug -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install fcakyon/phd-skills debug --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fcakyon/phd-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/debug .agents/skills/debug && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "debug" agent skill from https://github.com/fcakyon/phd-skills/tree/main/plugin/skills/debug into .agents/skills/debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debug", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add fcakyon/phd-skills --skill debug -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install fcakyon/phd-skills debug --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fcakyon/phd-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/debug .cursor/skills/debug && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "debug" agent skill from https://github.com/fcakyon/phd-skills/tree/main/plugin/skills/debug into .cursor/skills/debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debug", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/fcakyon/phd-skills.git --path plugin/skills/debug--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add fcakyon/phd-skills --skill debug -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install fcakyon/phd-skills debug --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fcakyon/phd-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/debug .gemini/skills/debug && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "debug" agent skill from https://github.com/fcakyon/phd-skills/tree/main/plugin/skills/debug into .gemini/skills/debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debug", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install fcakyon/phd-skills debugInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add fcakyon/phd-skills --skill debug -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/fcakyon/phd-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/debug .github/skills/debug && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "debug" agent skill from https://github.com/fcakyon/phd-skills/tree/main/plugin/skills/debug into .github/skills/debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debug", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add fcakyon/phd-skills --skill debug -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install fcakyon/phd-skills debug --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fcakyon/phd-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/debug .opencode/skills/debug && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "debug" agent skill from https://github.com/fcakyon/phd-skills/tree/main/plugin/skills/debug into .opencode/skills/debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debug", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
debug- GitHub stars
- 414
- Token cost
- ~1.3k tokens
- SKILL.md length
- 672 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
Evidence-before-action diagnosis of failing ML experiments. An agent skill from fcakyon/phd-skills.
- Works in 5 steps: cheap probes → hypothesis (labeled as hypothesis) → smoke run → …
- The user asks why a run is failing
- SKILL.md covers When to run, Five-step protocol, What to avoid and Output
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Debug is an agent skill from fcakyon/phd-skills. Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing, hanging, slow, producing weird metrics, has crashed, or asks to debug, diagnose, troubleshoot, or investigate a training issue.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Root cause analysis and Debugging. The repository describes itself as: PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more. The licence is MIT.
When your agent uses it
- The user asks why a run is failing
- Producing weird metrics
- Investigate a training issue
Example prompts
- “/debug”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 67acd61. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Debug loads about 1.3k tokens when it runs. Until then it costs about 113 tokens; SKILL.md has 672 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from fcakyon/phd-skills at commit 67acd61, republished under its MIT licence (© fcakyon). 672 words, ~1,314 tokens.
Download SKILL.mdSave it as
.claude/skills/debug/SKILL.md (or your agent's skills folder).- name
- debug
- description
- Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing, hanging, slow, producing weird metrics, has crashed, or asks to debug, diagnose, troubleshoot, or investigate a training issue.
Debug: evidence-before-action investigation
The most expensive class of mistake in ML debugging is asserting a cause based on plausibility, then attempting a "fix" that masks the real problem. This skill enforces the discipline of probe → hypothesis → smoke → controls → claim, in that order.
The agentic Stop hook routes here from reason when an assistant claims a cause without backing tool output.
When to run
The user just said any of:
- "why is X failing / diverging / NaN / OOM / hung / slow / crashed"
- "the loss is going up", "metrics look weird", "GPU util is 0"
- "debug this", "diagnose", "troubleshoot", "investigate this run"
- pasted a log excerpt asking what's wrong
Five-step protocol
Step 1: cheap probes
Before forming any hypothesis, gather the cheap evidence. None of these cost more than a few seconds:
Process state:
ps aux | grep -E '(python|train|torchrun|accelerate)' | grep -v grepIs the process still running? Zombie? Defunct? Multiple instances?
Kernel / system events:
dmesg | tail -100 # OOM kills, hardware errors, NFS errors
journalctl -xe --since "1 hour ago" | tail -50GPU state:
nvidia-smi
nvidia-smi --query-gpu=utilization.gpu,memory.used,temperature.gpu --format=csvIs the GPU even being used? Idle GPU during "training" means the process is blocked on data loading or has died.
Disk / filesystem:
df -h /path/to/run-dir
du -sh /path/to/run-dir/*Out of disk? Checkpoints not being written?
Log scrollback: Read the last few hundred lines of the training log. Don't trust the user's summary, they may have skimmed. Look for:
- exception tracebacks
- repeated "loss=NaN" or "grad_norm=Inf"
- early-stop announcements (the run may have completed normally)
- the last successful epoch / step (where did progress stop)
Checkpoint state:
ls -la /path/to/run-dir/checkpoints/When was the last checkpoint written? What does its size suggest? An empty .pt is different from a 2GB one cut short.
Step 2: hypothesis (labeled as hypothesis)
After the probe, state what might be happening, explicitly framed as a hypothesis:
"Hypothesis: the run is OOMing because dmesg shows
oom-kill3 minutes ago and the process is gone. Alternative hypotheses I haven't ruled out: (a) NFS write timeout, (b) explicit kill from a sibling process."
Never skip to "the cause is X." The hypothesis labels what you don't yet know.
Step 3: smoke run
The cheapest way to confirm or refute a hypothesis is to reproduce the failure shape under a controlled condition:
- OOM hypothesis: rerun with
batch_size=1for 1 step. If it survives, OOM is confirmed; if it fails the same way, OOM is wrong. - Data hypothesis: rerun with a synthetic in-memory dataset. If it works, the data path is implicated.
- Model hypothesis: forward pass only on a single batch with
eval()mode. Loss finite? Outputs sane? - Optimizer hypothesis: rerun with
lr=0. If the loss still explodes, the loss itself is broken (not the optimizer). - Distributed hypothesis: rerun on 1 GPU. If it works, DDP / NCCL is implicated.
A 30-second smoke beats a 30-minute restart-and-pray.
Show full SKILL.md (244 more words)Show less
Step 4: controls
If the smoke is ambiguous, run a control: change exactly one variable from the failing config and rerun the smoke. The differences narrow what mechanism is responsible.
Common control axes (change one at a time):
- single-source vs multi-source data
- default workers vs adjusted workers
- mixed-precision on vs off
- gradient checkpointing on vs off
- torch.compile on vs off
Step 5: claim cause
Only after evidence stacks up, probe, smoke, control, do you assert a cause. The claim should cite the specific tool output that proves it:
"Root cause: NFS write timeout. Evidence: dmesg shows
nfs server X not respondingat 14:23 (the same minute the last checkpoint was written), and the smoke withbatch=1reproduces the timeout. Recommended fix: bind-mount a local scratch dir for checkpoints and rsync to NFS at end of epoch."
If the evidence isn't stacking up, do not promote a hypothesis to a cause. Say "I don't yet know" and propose the next probe.
What to avoid
- "It's probably X, let me try Y" → no. Probe first.
- Restarting the run with a small change as the diagnostic. Smoke first, then restart deliberately.
- Citing only the user's narrative as evidence: re-read the actual log.
- Stopping at the first plausible cause when artifacts contradict it.
Output
A concise diagnostic report: (1) what the probes showed, (2) the hypothesis, (3) the smoke outcome, (4) the cause-or-uncertain verdict, (5) the recommended next action. Each claim cites the tool output that backs it.
© fcakyon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugin/skills/debug of fcakyon/phd-skills.
Open the folder on GitHubat commit 67acd61
Compare with similar skills
Debug next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Debug this skillfcakyon/phd-skills | 414 | — | ~1.3k | Automated safety check: Pass | MIT | |
| OpenLogi macOS Permissions TriageAprilNEA/OpenLogi | 23k | — | ~2.5k | Automated safety check: Notes | Apache-2.0 | |
| Bug Finder for daisyUIsaadeghi/daisyui | 43k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Root Cause Debugginggarrytan/gstack | 136k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Graph-Based Bug Tracingtirth8205/code-review-graph | 32k | 1 repos | ~287 | Automated safety check: Pass | MIT | |
| Systematic DebuggingChrisWiles/claude-code-showcase | 6.1k | 3 repos | ~1.2k | Automated safety check: Pass | None |
Similar skills
Bug Finder for daisyUI
saadeghi/daisyui
Investigates suspected bugs in the daisyUI monorepo through read-only analysis, then writes a decision-ready fix plan in tmp/bugs without changing any product code.
Root Cause Debugging
garrytan/gstack
Investigates bugs, errors and stack traces in phases and requires a root-cause hypothesis to be confirmed before any fix is written.
Graph-Based Bug Tracing
tirth8205/code-review-graph
Traces a bug through a code knowledge graph, following callers, callees and execution flow before opening source files, within a small token budget.
Systematic Debugging
ChrisWiles/claude-code-showcase
Applies a four-phase debugging routine that finds the root cause of a bug or failing test before any fix is written.
Debugging and Error Recovery
addyosmani/agent-skills
Applies a stop-the-line rule and a step-by-step triage when tests fail, builds break or something stops working, aiming at the root cause instead of guesses.
More from fcakyon/phd-skills
All 12 skills in this repoReproduce
fcakyon/phd-skills
End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments.
Compare
fcakyon/phd-skills
Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow.
Experiment Design
fcakyon/phd-skills
A skill your agent uses when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental evaluation strategies.
Latex Setup
fcakyon/phd-skills
A skill your agent uses when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation.
Launch
fcakyon/phd-skills
Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitoring setup, and restart-cleanup.
Literature Research
fcakyon/phd-skills
A skill your agent uses when the user wants to find related work, survey a research area, identify literature gaps, or discover open-source implementations.
Related
Categories
Questions about Debug
What does Debug do?
Evidence-before-action diagnosis of failing ML experiments. An agent skill from fcakyon/phd-skills. Debug is an agent skill from fcakyon/phd-skills. Evidence-before-action diagnosis of failing ML experiments.
When should I use Debug?
Debug fits situations like: the user asks why a run is failing; producing weird metrics; investigate a training issue.
How do I install Debug in Claude Code?
Run `npx skills add fcakyon/phd-skills --skill debug -a claude-code`. Or copy the skill folder (plugin/skills/debug in fcakyon/phd-skills) into .claude/skills/debug in your project. Claude Code loads it when a task matches its description.
How do I install Debug in Codex?
Run `npx skills add fcakyon/phd-skills --skill debug -a codex`. Or copy the skill folder (plugin/skills/debug in fcakyon/phd-skills) into .agents/skills/debug in your project. Codex loads it when a task matches its description.
Can I use Debug in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fcakyon/phd-skills --skill debug -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/debug, .gemini/skills/debug, .github/skills/debug and .opencode/skills/debug in your project.
What does Debug need to run?
SKILL.md names no scripts, command-line tools or credentials: Debug is instructions for the agent only.
Does Debug access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Debug safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Debug use?
Debug is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Debug use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Debug?
Skills that share tags, products or a category with Debug: OpenLogi macOS Permissions Triage (AprilNEA/OpenLogi, 23k stars), Bug Finder for daisyUI (saadeghi/daisyui, 43k stars), Root Cause Debugging (garrytan/gstack, 136k stars) and Graph-Based Bug Tracing (tirth8205/code-review-graph, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Debug?
fcakyon (a GitHub user) maintains it in fcakyon/phd-skills, which has 414 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 16, 2026.
Source: fcakyon/phd-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.